Processing system, processing method, and non-transitory storage medium

Abstract

An image acquisition unit ( 11 ) acquires a recognition processing image. A recognition unit ( 12 ) recognizes a product in the recognition processing image based on an estimation model. A registration unit ( 13 ) registers a result of the recognition in recognized product information. An output unit ( 14 ) outputs a result of the recognition. A correction reception unit ( 16 ) receives an input for correcting a result of the recognition. A correction unit ( 17 ) changes a result of the recognition to a result of the recognition after a correction, and also stores correction information in which a result of the recognition after a correction and the recognition processing image are associated with each other. A learning unit ( 18 ) performs relearning by using the recognition processing image stored as the correction information and updates the estimation model, when a number of the recognition processing image stored exceeds a predetermined value.

What is claimed is: 
     
       1. A processing system, comprising:
 at least one memory configured to store one or more instructions; and 
 at least one processor configured to execute the one or more instructions to: 
 acquire a recognition processing image including a product being a recognition target; 
 recognize a product in the recognition processing image, based on an estimation model generated by machine learning; 
 register a result of the recognition in recognized product information; 
 output a result of the recognition; 
 receive an input for correcting a result of the recognition; 
 change a result of the recognition being registered in the recognized product information to a result of the recognition after a correction, and also store, in storage unit, correction information in which a result of the recognition after a correction and the recognition processing image are associated with each other; and 
 perform relearning by using the recognition processing image stored as the correction information and updating the estimation model, when a number of the recognition processing image stored as the correction information exceeds a predetermined value. 
 
     
     
       2. The processing system according to  claim 1 , wherein the processor is further configured to execute the one or more instructions to:
 display a list of a plurality of results of the recognition being registered in the recognized product information, and 
 receive an input for specifying one from a plurality of results of the recognition displayed in a list, and an input for correcting a specified result of the recognition. 
 
     
     
       3. The processing system according to  claim 2 , wherein the processor is further configured to execute the one or more instructions to:
 receive an input of correct product identification information as an input for correcting a result of the recognition via a code reader, 
 acquire a correction image indicating a scene of work for causing the code reader to read product identification information provided to a product, and 
 determine, based on the correction image, a correction target among results of the recognition being registered in the recognized product information. 
 
     
     
       4. The processing system according to  claim 3 , wherein the processor is further configured to execute the one or more instructions to:
 recognize a product in the correction image, based on the estimation model, and 
 determine, as a correction target, a result of the recognition that coincides with a result of recognition in the correction image among results of the recognition being registered in the recognized product information. 
 
     
     
       5. The processing system according to  claim 3 , wherein the processor is further configured to execute the one or more instructions to determine a correction target, based on a degree of similarity between a feature value of an appearance of a product in the correction image and a feature value of an appearance of a product in the recognition processing image. 
     
     
       6. The processing system according to  claim 1 , wherein the processor is further configured to execute the one or more instructions to receive an input of correct product identification information as an input for correcting a result of the recognition. 
     
     
       7. The processing system according to  claim 6 , wherein the processor is further configured to execute the one or more instructions to receive an input of correct product identification information via a code reader. 
     
     
       8. A processing method, comprising,
 by a computer: 
 acquiring a recognition processing image including a product being a recognition target; 
 recognizing a product in the recognition processing image, based on an estimation model generated by machine learning; 
 registering a result of the recognition in recognized product information; 
 outputting a result of the recognition; 
 receiving an input for correcting a result of the recognition; 
 changing a result of the recognition being registered in the recognized product information to a result of the recognition after a correction, and also storing, in storage unit, correction information in which a result of the recognition after a correction and the recognition processing image are associated with each other; and 
 performing relearning by using the recognition processing image stored as the correction information and updating the estimation model, when a number of the recognition processing image stored as the correction information exceeds a predetermined value. 
 
     
     
       9. A non-transitory storage medium storing a program causing a computer to:
 acquire a recognition processing image including a product being a recognition target; 
 recognize a product in the recognition processing image, based on an estimation model generated by machine learning; 
 register a result of the recognition in recognized product information; 
 output a result of the recognition; 
 receive an input for correcting a result of the recognition; 
 change a result of the recognition being registered in the recognized product information to a result of the recognition after a correction, and also store, in storage unit, correction information in which a result of the recognition after a correction and the recognition processing image are associated with each other; and 
 perform relearning by using the recognition processing image stored as the correction information and updating the estimation model, when a number of the recognition processing image stored as the correction information exceeds a predetermined value.